Renewable energy forecasting services comprise various modules for intra-day and day-ahead forecasts. This work specifically addresses day-ahead forecasts, utilizing specifications based on endogenous, historical measurements. These specifications are designed to be computationally efficient, requiring fewer input variables and less training data. Such weather-independent specifications serve as benchmarks against the more computationally demanding forecasts based on numerical weather predictions. A series of experiments, designed to simulate the real-world application of an online system, were conducted on sliding windows of back-contact photovoltaic (installed at KAUST, Saudi Arabia) output series, solar irradiance recorded in Hawaii, and simulated data. Our analysis evaluated 24 specifications, which are variants of (i) functional time series models (including two novel shrinkage procedures); (ii) time series nearest neighbor schemes; (iii) exponential smoothing procedures; (iv) autoregressive integrated moving average processes; (v) automatic techniques based on time series decomposition; and (vi) the persistence model. In addition to employing outlier-robust accuracy metrics, such as mean absolute error, our evaluation also prioritized prediction-interval accuracy, quantified by the mean scaled interval score. Our findings suggest that practitioners can achieve significant improvements over the persistence model by forecasting daily profiles using adaptive nonparametric or functional data analysis-based procedures. Moreover, applying shrinkage to nearest neighbor (NN) forecasts toward smooth, average daily profiles significantly enhances NN performance. Conversely, some popular, computationally intensive models fail to perform adequately to justify their additional cost.

1.
P.
Pinson
,
C.
Chevallier
, and
G. N.
Kariniotakis
, “
Trading wind generation from short-term probabilistic forecasts of wind power
,”
IEEE Trans. Power Syst.
22
,
1148
1156
(
2007
).
2.
B.
Kraas
,
M.
Schroedter-Homscheidt
, and
R.
Madlener
, “
Economic merits of a state-of-the-art concentrating solar power forecasting system for participation in the Spanish electricity market
,”
Sol. Energy
93
,
244
255
(
2013
).
3.
A.
Aslam
,
N.
Ahmed
,
S. A.
Qureshi
,
M.
Assadi
, and
N.
Ahmed
, “
Advances in solar PV systems; A comprehensive review of PV performance, influencing factors, and mitigation techniques
,”
Energies
15
,
7595
(
2022
).
4.
C. L.
Dewangan
,
S.
Singh
, and
S.
Chakrabarti
, “
Combining forecasts of day-ahead solar power
,”
Energy
202
,
117743
(
2020
).
5.
H. T.
Pedro
and
C. F.
Coimbra
, “
Assessment of forecasting techniques for solar power production with no exogenous inputs
,”
Sol. Energy
86
,
2017
2028
(
2012
).
6.
J.
Antonanzas
,
N.
Osorio
,
R.
Escobar
,
R.
Urraca
,
F. M.
de Pison
, and
F.
Antonanzas-Torres
, “
Review of photovoltaic power forecasting
,”
Sol. Energy
136
,
78
111
(
2016
).
7.
L.
Liu
,
M.
Zhan
, and
Y.
Bai
, “
A recursive ensemble model for forecasting the power output of photovoltaic systems
,”
Sol. Energy
189
,
291
298
(
2019
).
8.
J. Á. G.
Ordiano
,
S.
Waczowicz
,
M.
Reischl
,
R.
Mikut
, and
V.
Hagenmeyer
, “
Photovoltaic power forecasting using simple data-driven models without weather data
,”
Comput. Sci.-Res. Dev.
32
,
237
246
(
2017
).
9.
E.
Sharma
, “
Energy forecasting based on predictive data mining techniques in smart energy grids
,”
Energy Inf.
1
,
367
373
(
2018
).
10.
F.
Petropoulos
and
I.
Svetunkov
, “
A simple combination of univariate models
,”
Int. J. Forecast.
36
,
110
115
(
2020
).
11.
S.
Sheoran
and
S.
Pasari
, “
Efficacy and application of the window-sliding ARIMA for daily and weekly wind speed forecasting
,”
J. Renewable Sustainable Energy
14
,
053305
(
2022
).
12.
Y.
Zhang
,
J.
Wang
, and
X.
Wang
, “
Review on probabilistic forecasting of wind power generation
,”
Renewable Sustainable Energy Rev.
32
,
255
270
(
2014
).
13.
C.
Voyant
,
G.
Notton
,
J.-L.
Duchaud
,
J.
Almorox
, and
Z. M.
Yaseen
, “
Solar irradiation prediction intervals based on box–cox transformation and univariate representation of periodic autoregressive model
,”
Renewable Energy Focus
33
,
43
53
(
2020
).
14.
E. V.
Kerschaver
and
G.
Beaucarne
, “
Back-contact solar cells: A review
,”
Prog. Photovoltaics
14
,
107
123
(
2006
).
15.
T.
Laloë
, “
A k-nearest neighbor approach for functional regression
,”
Stat. Probab. Lett.
78
,
1189
1193
(
2008
).
16.
F.
Martínez
,
M. P.
Frías
,
M. D.
Pérez
, and
A. J.
Rivera
, “
A methodology for applying k-nearest neighbor to time series forecasting
,”
Artif. Intell. Rev.
52
,
2019
2037
(
2019
).
17.
P. H.
Franses
and
E.
Janssens
, “
This time it is different! or not? discounting past data when predicting the future
,”
Ann. Financ. Econ.
13
,
1850005
(
2018
).
18.
D.
Yang
,
S.
Alessandrini
,
J.
Antonanzas
,
F.
Antonanzas-Torres
,
V.
Badescu
,
H. G.
Beyer
,
R.
Blaga
,
J.
Boland
,
J. M.
Bright
,
C. F.
Coimbra
et al, “
Verification of deterministic solar forecasts
,”
Sol. Energy
210
,
20
37
(
2020
).
19.
D.
Kothona
,
K.
Spyropoulos
,
C.
Valelis
,
C.
Koutsis
,
K. C.
Chatzisavvas
, and
G. C.
Christoforidis
, “
Deep learning forecasting tool facilitating the participation of photovoltaic systems into day-ahead and intra-day electricity markets
,”
Sustainable Energy, Grids Networks
36
,
101149
(
2023
).
20.
Y.
Kamarianakis
,
W.
Shen
, and
L.
Wynter
, “
Real-time road traffic forecasting using regime-switching space-time models and adaptive lasso
,”
Appl. Stochastic Models Bus. Ind.
28
,
297
315
(
2012
).
21.
P. S.
Cowpertwait
and
A. V.
Metcalfe
,
Introductory Time Series with R
(
Springer
,
2009
).
22.
T.-H.
Li
,
Time Series with Mixed Spectra
(
CRC Press
,
2013
).
23.
A. V.
Metcalfe
and
P. S.
Cowpertwait
,
Introductory Time Series with R
(
Springer
,
2009
).
24.
S. N.
Wood
,
Generalized Additive Models: An Introduction with R
(
CRC Press
,
2017
).
25.
A.-M.
Staicu
and
P. S.
Young
,
Short Course on Applied Functional Data Analysis
(
NCSU
,
2016
).
26.
M. H.
Kutner
,
C. J.
Nachtsheim
,
J.
Neter
,
W.
Li
et al,
Applied Linear Statistical Models
(
McGraw-Hill Irwin
,
Boston
,
2005
), Vol.
5
.
27.
I.
Svetunkov
,
Forecasting and Analytics with the Augmented Dynamic Adaptive Model (ADAM)
(
Chapman and Hall/CRC
,
2023
).
28.
S. N.
Wood
,
N.
Pya
, and
B.
Säfken
, “
Smoothing parameter and model selection for general smooth models
,”
J. Am. Stat. Assoc.
111
,
1548
1563
(
2016
).
29.
R.
Koenker
,
V.
Chernozhukov
,
X.
He
, and
L.
Peng
,
Handbook of Quantile Regression
(CRC Press,
2017
).
30.
Y.
Chu
,
B.
Urquhart
,
S. M.
Gohari
,
H. T.
Pedro
,
J.
Kleissl
, and
C. F.
Coimbra
, “
Short-term reforecasting of power output from a 48 MWe solar PV plant
,”
Sol. Energy
112
,
68
77
(
2015
).
31.
H. T.
Pedro
and
C. F.
Coimbra
, “
Short-term irradiance forecastability for various solar micro-climates
,”
Sol. Energy
122
,
587
602
(
2015
).
32.
S.
Makridakis
,
E.
Spiliotis
, and
V.
Assimakopoulos
, “
The m4 competition: 100,000 time series and 61 forecasting methods
,”
Int. J. Forecast.
36
,
54
74
(
2020
).
33.
D.
Anderson
and
K.
Burnham
,
Model Selection and Multi-Model Inference
, 2nd ed. (
Springer-Verlag
,
NY
,
2004
), Vol.
63
, p.
10
.
34.
R.
Hyndman
,
A. B.
Koehler
,
J. K.
Ord
, and
R. D.
Snyder
,
Forecasting with Exponential Smoothing: The State Space Approach
(
Springer Science & Business Media
,
2008
).
35.
P. J.
Brockwell
and
R. A.
Davis
,
Time Series: Theory and Methods
(
Springer Science & Business Media
,
2009
).
36.
R. J.
Hyndman
and
Y.
Khandakar
, “
Automatic time series forecasting: The forecast package for R
,”
J. Stat. Software
27
,
1
22
(
2008
).
37.
R. J.
Hyndman
and
G.
Athanasopoulos
,
Forecasting: Principles and Practice
(
OTexts
,
2018
).
38.
S. J.
Taylor
and
B.
Letham
, “
Forecasting at scale
,”
Am. Stat.
72
,
37
45
(
2018
).
39.
N.
Matloff
,
Statistical Regression and Classification: From Linear Models to Machine Learning
(
Chapman and Hall/CRC
,
2017
).
40.
N. K.
Ahmed
,
A. F.
Atiya
,
N. E.
Gayar
, and
H.
El-Shishiny
, “
An empirical comparison of machine learning models for time series forecasting
,”
Econ. Rev.
29
,
594
621
(
2010
).
41.
F.
Martínez
,
M. P.
Frías
,
F.
Charte
, and
A. J.
Rivera
, “
Time series forecasting with KNN in r: The TSKNN package
,”
R J.
11
,
229
(
2019
).
42.
S. F.
Crone
,
M.
Hibon
, and
K.
Nikolopoulos
, “
Advances in forecasting with neural networks? empirical evidence from the nn3 competition on time series prediction
,”
Int. J. Forecast.
27
,
635
660
(
2011
).
43.
Y.
Chen
,
T.
Koch
,
K. G.
Lim
,
X.
Xu
, and
N.
Zakiyeva
, “
A review study of functional autoregressive models with application to energy forecasting
,”
Wiley Interdiscip. Rev.
13
,
e1525
(
2021
).
44.
J.-L.
Wang
,
J.-M.
Chiou
, and
H.-G.
Müller
, “
Functional data analysis
,”
Annu. Rev. Stat. Appl.
3
,
257
295
(
2016
).
45.
F.
Rahmani
and
M. H.
Fattahi
, “
Investigation of denoising effects on forecasting models by statistical and nonlinear dynamic analysis
,”
J. Water Clim. Change
12
,
1614
1630
(
2021
).
46.
J.
Ramsay
,
G.
Hooker
, and
S.
Graves
,
Functional Data Analysis with R and MATLAB (Springer Science & Business Media
,
2009
).
47.
M.
Febrero-Bande
and
M. O.
De La Fuente
, “
Statistical computing in functional data analysis: The R package fda. usc
,”
J. Stat. Software
51
,
1
28
(
2012
).
48.
H.
Shang
et al, “
ftsa: An R package for analyzing functional time series
,” R J. 5, 64 (
2013
).
49.
R. J.
Hyndman
and
H. L.
Shang
, “
Forecasting functional time series
,”
J. Korean Stat. Soc.
38
,
199
211
(
2009
).
50.
M. H.
Gruber
,
Improving Efficiency by Shrinkage: The James-Stein and Ridge Regression Estimators
(
Routledge
,
2017
).
51.
T.
Hastie
,
R.
Tibshirani
,
J. H.
Friedman
, and
J. H.
Friedman
,
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
(
Springer
,
2009
), Vol.
2
.
52.
D.
Yang
, “
Making reference solar forecasts with climatology, persistence, and their optimal convex combination
,”
Sol. Energy
193
,
981
985
(
2019
).
53.
G.
Claeskens
,
J. R.
Magnus
,
A. L.
Vasnev
, and
W.
Wang
, “
The forecast combination puzzle: A simple theoretical explanation
,”
Int. J. Forecast.
32
,
754
762
(
2016
).
54.
T.
Gneiting
, “
Making and evaluating point forecasts
,”
J. Am. Stat. Assoc.
106
,
746
762
(
2011
).
55.
C. J.
Willmott
and
K.
Matsuura
, “
Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance
,”
Clim. Res.
30
,
79
82
(
2005
).
56.
R. J.
Hyndman
and
A. B.
Koehler
, “
Another look at measures of forecast accuracy
,”
Int. J. Forecast.
22
,
679
688
(
2006
).
57.
C.
Tofallis
, “
A better measure of relative prediction accuracy for model selection and model estimation
,”
J. Oper. Res. Soc.
66
,
1352
1362
(
2015
).
58.
A.
Elías
,
R.
Jiménez
, and
H. L.
Shang
, “
On projection methods for functional time series forecasting
,”
J. Multivar. Anal.
189
,
104890
(
2022
).
59.
T.
Gneiting
and
A. E.
Raftery
, “
Strictly proper scoring rules, prediction, and estimation
,”
J. Am. Stat. Assoc.
102
,
359
378
(
2007
).
60.
Y.
Kamarianakis
,
Y.
Pantazis
,
E.
Kalligiannaki
,
K.
Kotsovos
,
I.
Gereige
,
M.
Abdullah
,
A.
Tzavaras
, and
T.
Katsaounis
, “
Day-ahead forecasting of solar irradiance: KNN-based ensembles
,” in
Proceedings of the 8th World Conference on Photovoltaic Energy Conversion
(
2022
).
61.
Y.
Kamarianakis
,
Y.
Pantazis
,
E.
Kalligiannaki
,
K.
Kotsovos
,
I.
Gereige
,
M.
Abdullah
,
A.
Tzavaras
, and
T.
Katsaounis
, “
KNN-based ensembles for day-ahead solar power output forecasting
,” in
Proceedings of EuroSun2022: ISES and IEA SHC International Conference on Solar Energy for Buildings and Industry
(
2022
).
62.
Y.
Kamarianakis
,
Y.
Pantazis
,
E.
Kalligiannaki
,
T. D.
Katsaounis
,
K.
Kotsovos
,
I.
Gereige
,
M.
Abdullah
,
A.
Jamal
, and
A.
Tzavaras
, “
Day-ahead forecasting of solar irradiance & pv power output through statistical machine learning methods
,” in
2022 Saudi Arabia Smart Grid (SASG)
(
IEEE
,
2022
) pp.
1
5
.
63.
M.
Sengupta
and
A.
Andreas
, “
Oahu solar measurement grid (1-year archive): 1-second solar irradiance; Oahu, Hawaii (data)
,” Report No. NREL/DA-5500-5506,
2010
.
64.
C.
Voyant
and
G.
Notton
, “
Solar irradiation nowcasting by stochastic persistence: A new parsimonious, simple and efficient forecasting tool
,”
Renewable Sustainable Energy Rev.
92
,
343
352
(
2018
).
65.
B. E.
Flores
, “
The utilization of the Wilcoxon test to compare forecasting methods: A note
,”
Int. J. Forecast.
5
,
529
535
(
1989
).
66.
D. J.
Benjamin
and
J. O.
Berger
, “
Three recommendations for improving the use of p-values
,”
Am. Stat.
73
,
186
191
(
2019
).
67.
P. J.
Avery
and
D. A.
Henderson
, “
Fitting Markov chain models to discrete state series such as DNA sequences
,”
J. R. Stat. Soc. Ser. C
48
,
53
61
(
1999
).
68.
G. A.
Spedicato
,
T. S.
Kang
,
S. B.
Yalamanchi
,
D.
Yadav
, and
I.
Cordón
, “
The markovchain package: A package for easily handling discrete Markov chains in R
,”
2016
.
69.
E.
Sidrow
,
N.
Heckman
,
S. M.
Fortune
,
A. W.
Trites
,
I.
Murphy
, and
M.
Auger-Méthé
, “
Modelling multi-scale, state-switching functional data with hidden Markov models
,”
Can. J. Stat.
50
,
327
356
(
2022
).
You do not currently have access to this content.